blob: 0938ff4862e3070a4e3aab2c19ec391e6a82ce09 (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
|
#!/bin/bash
# Run vanilla and contextual baselines with matching datasets (math-hard, math-500, bigcodebench)
# Same setup as rag/reflection/rag_vector 60s experiments for fair comparison
echo "Starting baseline experiments (vanilla + contextual)..."
echo "$(date '+%Y-%m-%d %H:%M:%S')"
# Vanilla (no personalization)
echo "Starting vanilla..."
python collaborativeagents/scripts/run_experiments.py \
--methods vanilla \
--datasets math-hard,math-500,bigcodebench \
--n-profiles 60 \
--n-sessions 60 \
--max-turns 10 \
--use-vllm \
--vllm-agent-url http://localhost:8003/v1 \
--vllm-user-url http://localhost:8004/v1 \
--use-batch-processing \
--batch-size 4 \
--parallel-profiles 20 \
--profile-path collaborativeagents/data/complex_profiles_v2/profiles_200.jsonl \
--output-dir collaborativeagents/results/vanilla_60s \
2>&1 | tee collaborativeagents/results/vanilla_60s.log
echo "Vanilla completed at $(date '+%Y-%m-%d %H:%M:%S')"
# Contextual (full history in context)
echo "Starting contextual..."
python collaborativeagents/scripts/run_experiments.py \
--methods contextual \
--datasets math-hard,math-500,bigcodebench \
--n-profiles 60 \
--n-sessions 60 \
--max-turns 10 \
--use-vllm \
--vllm-agent-url http://localhost:8003/v1 \
--vllm-user-url http://localhost:8004/v1 \
--use-batch-processing \
--batch-size 4 \
--parallel-profiles 20 \
--profile-path collaborativeagents/data/complex_profiles_v2/profiles_200.jsonl \
--output-dir collaborativeagents/results/contextual_60s \
2>&1 | tee collaborativeagents/results/contextual_60s.log
echo "Both baselines completed at $(date '+%Y-%m-%d %H:%M:%S')"
|
